© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81598
    Prev
    Next
    INDEX
    Explanations

    press release dateline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h6>
    -0.90
    “.
    -0.87
    𝕪
    -0.84
    “,
    -0.83
     godzin
    -0.81
    “...
    -0.79
    “:
    -0.75
     geluid
    -0.75
    “-
    -0.75
    ely
    -0.75
    POSITIVE LOGITS
    …"
    0.92
    strze
    0.80
    хая
    0.74
    𝘿
    0.72
    捶
    0.71
     gerais
    0.70
    作詞
    0.68
     Adjusted
    0.67
    きっかけ
    0.67
    ソコン
    0.67
    Activations Density 0.164%

    No Known Activations